[2021-03-23 07:03:49,374] [INFO] [logging.py:60:log_dist] [Rank 0] DeepSpeed info: version=0.3.13, git-hash=unknown, git-branch=unknown
[2021-03-23 07:03:49,407] [INFO] [engine.py:77:_initialize_parameter_parallel_groups] data_parallel_size: 1, parameter_parallel_size: 1
Using /home/jovyan/.cache/torch_extensions as PyTorch extensions root...
Creating extension directory /home/jovyan/.cache/torch_extensions/fused_adam...
Detected CUDA files, patching ldflags
Emitting ninja build file /home/jovyan/.cache/torch_extensions/fused_adam/build.ninja...
Building extension module fused_adam...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
---------------------------------------------------------------------------
CalledProcessError                        Traceback (most recent call last)
~/.local/lib/python3.6/site-packages/torch/utils/cpp_extension.py in _run_ninja_build(build_directory, verbose, error_prefix)
   1672             check=True,
-> 1673             env=env)
   1674     except subprocess.CalledProcessError as e:

/usr/lib/python3.6/subprocess.py in run(input, timeout, check, *popenargs, **kwargs)
    437             raise CalledProcessError(retcode, process.args,
--> 438                                      output=stdout, stderr=stderr)
    439     return CompletedProcess(process.args, retcode, stdout, stderr)

CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1.

The above exception was the direct cause of the following exception:

RuntimeError                              Traceback (most recent call last)
<ipython-input-24-3435b262f1ae> in <module>
----> 1 trainer.train()

~/.local/lib/python3.6/site-packages/transformers/trainer.py in train(self, resume_from_checkpoint, trial, **kwargs)
    901         delay_optimizer_creation = self.sharded_ddp is not None and self.sharded_ddp != ShardedDDPOption.SIMPLE
    902         if self.args.deepspeed:
--> 903             model, optimizer, lr_scheduler = init_deepspeed(self, num_training_steps=max_steps)
    904             self.model = model.module
    905             self.model_wrapped = model  # will get further wrapped in DDP

~/.local/lib/python3.6/site-packages/transformers/integrations.py in init_deepspeed(trainer, num_training_steps)
    416         model=model,
    417         model_parameters=model_parameters,
--> 418         config_params=config,
    419     )
    420 

~/.local/lib/python3.6/site-packages/deepspeed/__init__.py in initialize(args, model, optimizer, model_parameters, training_data, lr_scheduler, mpu, dist_init_required, collate_fn, config_params)
    123                                  dist_init_required=dist_init_required,
    124                                  collate_fn=collate_fn,
--> 125                                  config_params=config_params)
    126     else:
    127         assert mpu is None, "mpu must be None with pipeline parallelism"

~/.local/lib/python3.6/site-packages/deepspeed/runtime/engine.py in __init__(self, args, model, optimizer, model_parameters, training_data, lr_scheduler, mpu, dist_init_required, collate_fn, config_params, dont_change_device)
    181         self.lr_scheduler = None
    182         if model_parameters or optimizer:
--> 183             self._configure_optimizer(optimizer, model_parameters)
    184             self._configure_lr_scheduler(lr_scheduler)
    185             self._report_progress(0)

~/.local/lib/python3.6/site-packages/deepspeed/runtime/engine.py in _configure_optimizer(self, client_optimizer, model_parameters)
    596                 logger.info('Using client Optimizer as basic optimizer')
    597         else:
--> 598             basic_optimizer = self._configure_basic_optimizer(model_parameters)
    599             if self.global_rank == 0:
    600                 logger.info(

~/.local/lib/python3.6/site-packages/deepspeed/runtime/engine.py in _configure_basic_optimizer(self, model_parameters)
    670                     optimizer = FusedAdam(model_parameters,
    671                                           **optimizer_parameters,
--> 672                                           adam_w_mode=effective_adam_w_mode)
    673 
    674         elif self.optimizer_name() == LAMB_OPTIMIZER:

~/.local/lib/python3.6/site-packages/deepspeed/ops/adam/fused_adam.py in __init__(self, params, lr, bias_correction, betas, eps, adam_w_mode, weight_decay, amsgrad, set_grad_none)
     70         self.set_grad_none = set_grad_none
     71 
---> 72         fused_adam_cuda = FusedAdamBuilder().load()
     73         # Skip buffer
     74         self._dummy_overflow_buf = torch.cuda.IntTensor([0])

~/.local/lib/python3.6/site-packages/deepspeed/ops/op_builder/builder.py in load(self, verbose)
    213             return importlib.import_module(self.absolute_name())
    214         else:
--> 215             return self.jit_load(verbose)
    216 
    217     def jit_load(self, verbose=True):

~/.local/lib/python3.6/site-packages/deepspeed/ops/op_builder/builder.py in jit_load(self, verbose)
    250             extra_cuda_cflags=self.nvcc_args(),
    251             extra_ldflags=self.extra_ldflags(),
--> 252             verbose=verbose)
    253         build_duration = time.time() - start_build
    254         if verbose:

~/.local/lib/python3.6/site-packages/torch/utils/cpp_extension.py in load(name, sources, extra_cflags, extra_cuda_cflags, extra_ldflags, extra_include_paths, build_directory, verbose, with_cuda, is_python_module, is_standalone, keep_intermediates)
   1089         is_python_module,
   1090         is_standalone,
-> 1091         keep_intermediates=keep_intermediates)
   1092 
   1093 

~/.local/lib/python3.6/site-packages/torch/utils/cpp_extension.py in _jit_compile(name, sources, extra_cflags, extra_cuda_cflags, extra_ldflags, extra_include_paths, build_directory, verbose, with_cuda, is_python_module, is_standalone, keep_intermediates)
   1300                         verbose=verbose,
   1301                         with_cuda=with_cuda,
-> 1302                         is_standalone=is_standalone)
   1303             finally:
   1304                 baton.release()

~/.local/lib/python3.6/site-packages/torch/utils/cpp_extension.py in _write_ninja_file_and_build_library(name, sources, extra_cflags, extra_cuda_cflags, extra_ldflags, extra_include_paths, build_directory, verbose, with_cuda, is_standalone)
   1405         build_directory,
   1406         verbose,
-> 1407         error_prefix=f"Error building extension '{name}'")
   1408 
   1409 

~/.local/lib/python3.6/site-packages/torch/utils/cpp_extension.py in _run_ninja_build(build_directory, verbose, error_prefix)
   1681         if hasattr(error, 'output') and error.output:  # type: ignore
   1682             message += f": {error.output.decode()}"  # type: ignore
-> 1683         raise RuntimeError(message) from e
   1684 
   1685 

RuntimeError: Error building extension 'fused_adam'

Collecting environment information...
PyTorch version: 1.8.0+cu101
Is debug build: False
CUDA used to build PyTorch: 10.1
ROCM used to build PyTorch: N/A

OS: Ubuntu 18.04.5 LTS (x86_64)
GCC version: (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0
Clang version: Could not collect
CMake version: Could not collect

Python version: 3.6 (64-bit runtime)
Is CUDA available: True
CUDA runtime version: 10.1.243
GPU models and configuration: 
GPU 0: Tesla V100-SXM2-32GB
GPU 1: Tesla V100-SXM2-32GB

Nvidia driver version: 450.51.06
cuDNN version: /usr/lib/x86_64-linux-gnu/libcudnn.so.7.6.4
HIP runtime version: N/A
MIOpen runtime version: N/A

Versions of relevant libraries:
[pip3] kubeflow-pytorchjob==0.1.3
[pip3] numpy==1.18.5
[pip3] torch==1.8.0+cu101
[pip3] torchvision==0.8.1
[conda] Could not collect

nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2019 NVIDIA Corporation
Built on Sun_Jul_28_19:07:16_PDT_2019
Cuda compilation tools, release 10.1, V10.1.243